Paper: Minimum Cut Model For Spoken Lecture Segmentation

ACL ID P06-1004
Title Minimum Cut Model For Spoken Lecture Segmentation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006
Authors

We consider the task of unsupervised lec- ture segmentation. We formalize segmen- tation as a graph-partitioning task that op- timizes the normalized cut criterion. Our approach moves beyond localized com- parisons and takes into account long- range cohesion dependencies. Our results demonstrate that global analysis improves the segmentation accuracy and is robust in the presence of speech recognition errors.